Rationale for Reward Score Difference
A reward model is trained by minimizing a loss function that involves applying a sigmoid function to the difference between the scalar scores of a preferred response and a rejected response. Explain the primary reason why this training objective focuses on maximizing the difference between these two scores, rather than simply trying to maximize the score of the preferred response alone.
0
1
Tags
Ch.4 Alignment - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Analysis in Bloom's Taxonomy
Cognitive Psychology
Psychology
Social Science
Empirical Science
Science
Related
Optimal Reward Model Parameter Estimation
A reward model is being trained using a loss function calculated as the negative log of a sigmoid function applied to the difference in scores between a preferred response () and a rejected response (). For a single training instance, the model outputs a score of for the preferred response and for the rejected response. How will this specific outcome influence the model's parameter update for this step?
Reward Model Loss Contribution Analysis
Rationale for Reward Score Difference